Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3612 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1797. Min Range: -8.1797
Max Act: 8.1797. Min Act: -0.1700
Data Index: 3294491 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1797. Min Range: -8.1797
Max Act: 8.1797. Min Act: -0.1700
Data Index: 2445980 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1797. Min Range: -8.1797
Max Act: 8.0859. Min Act: -0.1700
Data Index: 6114233 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1797. Min Range: -8.1797
Max Act: 8.0859. Min Act: -0.1700
Data Index: 7130765 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1797. Min Range: -8.1797
Max Act: 8.0234. Min Act: -0.1700
Data Index: 1522826 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1797. Min Range: -8.1797
Max Act: 8.0547. Min Act: -0.1700
Data Index: 5730208 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1797. Min Range: -8.1797
Max Act: 7.9922. Min Act: -0.1700
Data Index: 5664754 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1797. Min Range: -8.1797
Max Act: 7.9922. Min Act: -0.1700
Data Index: 4342993 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1797. Min Range: -8.1797
Max Act: 7.9297. Min Act: -0.1700
Data Index: 4795310 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1797. Min Range: -8.1797
Max Act: 7.9609. Min Act: -0.1700
Data Index: 8142708 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1797. Min Range: -8.1797
Max Act: 7.9297. Min Act: -0.1700
Data Index: 2795909 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1797. Min Range: -8.1797
Max Act: 7.8984. Min Act: -0.1700
Data Index: 7057952 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1797. Min Range: -8.1797
Max Act: 7.8047. Min Act: -0.1700
Data Index: 3203982 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1797. Min Range: -8.1797
Max Act: 7.8047. Min Act: -0.1700
Data Index: 405060 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1797. Min Range: -8.1797
Max Act: 7.8359. Min Act: -0.1700
Data Index: 6824133 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1797. Min Range: -8.1797
Max Act: 7.8359. Min Act: -0.1700
Data Index: 2556635 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1797. Min Range: -8.1797
Max Act: 7.8359. Min Act: -0.1700
Data Index: 5153009 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1797. Min Range: -8.1797
Max Act: 7.8047. Min Act: -0.1700
Data Index: 341127 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1797. Min Range: -8.1797
Max Act: 7.7422. Min Act: -0.1700
Data Index: 554178 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1797. Min Range: -8.1797
Max Act: 7.7734. Min Act: -0.1700
Data Index: 591445 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #19